Abstract:

Graph Convolutional Networks （GCNs） have demonstrated significant potential in graph representation learning. However， existing methods still exhibit limitations in learning global topological relationships and fusing topological structure with attribute features. To address these challenges， a Graph Convolutional Network enhanced by Graph Diffusion and Dual-View feature learning （GCN-GDDV） was proposed. Firstly， a generalized graph diffusion mechanism was introduced to construct diffusion graphs containing global topological structure information. Then these diffusion graphs were combined with attribute-feature-based K-Nearest Neighbor （KNN） graphs to perform dual-view feature learning via GCN， capturing relationship dependencies in the global structure and the semantic similarities of node attributes， respectively. Finally， an attention network was designed to adaptively fuse topological structures and attribute features. Node classification experimental results on three benchmark graph datasets demonstrate that GCN-GDDV outperforms the suboptimal method， achieving average improvements of 1.78%， 1.60%， and 0.30% in accuracy， Macro-F1， and Micro-F1 metrics， respectively.

Key words: Graph Convolutional Network (GCN), graph diffusion, dual-view feature learning, attention mechanism, node classification

摘要：

图卷积网络（GCN）在图表示学习领域已展现了强大的潜力，然而，现有的GCN方法在全局拓扑关系学习以及拓扑结构和属性特征融合方面仍存在局限性。针对该问题，提出一种图扩散与双视图特征学习增强的图卷积网络（GCN-GDDV）。该网络首先引入广义图扩散机制构建包含全局拓扑结构信息的扩散图；随后，结合属性特征K近邻图进行基于GCN的双视图特征学习，以分别捕捉全局结构关系依赖与节点属性的语义相似性；最后，设计注意力网络实现拓扑结构和属性特征的自适应融合。在3个常用图数据集上进行节点分类实验的结果表明：GCN-GDDV相较于次优方法在准确率、Macro-F1和Micro-F1指标上分别提升1.78%、1.60%和0.30%。

关键词: 图卷积网络, 图扩散, 双视图特征学习, 注意力机制, 节点分类